G
Guo-Jun Qi
Researcher at Huawei
Publications - 263
Citations - 12701
Guo-Jun Qi is an academic researcher from Huawei. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 53, co-authored 248 publications receiving 9928 citations. Previous affiliations of Guo-Jun Qi include China University of Science and Technology & University of Science and Technology of China.
Papers
More filters
Posted Content
Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes
TL;DR: A model for revealing the functional relationships between text and image features as to directly transfer intermodal and intramodal labels to annotate the images and evaluates the effectiveness on an image classification task and shows the effectiveness with respect to the other compared algorithms.
Journal Article
Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
Xiang Gao,Wei Hu,Guo-Jun Qi +2 more
TL;DR: Zhang et al. as discussed by the authors proposed a self-supervised learning paradigm of Multi-View Transformation Equivariant Representations (MV-TER), exploiting the equivariant transformations of a 3D object and its projected multiple views.
Journal ArticleDOI
Latent Dirichlet Truth Discovery: Separating Trustworthy and Untrustworthy Components in Data Sources
TL;DR: A latent Dirichlet truth (LDT) discovery model is proposed that defines a random field over all the possible configurations of the trustworthy degrees of sources and facts, and the most probable configuration is inferred by a maximum a posteriori criterion over the observed claims.
Proceedings ArticleDOI
Cross-modal hashing through ranking subspace learning
TL;DR: A novel hash learning framework that maps high-dimensional multimodal data into a common Hamming space where the cross-modal similarity can be measured using Hamming distance is proposed.
Proceedings ArticleDOI
Cascade Attention Machine for Occluded Landmark Detection in 2D X-Ray Angiography
TL;DR: A novel Cascade Attention Machine (CAM) model is proposed that borrows the idea of how human experts localize the catheter tip by first per-forming landmark detection when occlusion does not hap-pen, then leveraging this information as prior knowledge to assist the occluded detection.